eCite Digital Repository

Supervised machine learning algorithm selection for condition monitoring of induction motors


Rajapaksha, NN and Jayasinghe Arachchillage, SDG and Enshaei, H and Sembukutti Vidanelage, BJ, Supervised machine learning algorithm selection for condition monitoring of induction motors, Proceedings of the 2021 IEEE Annual Southern Power Electronics Conference (SPEC), 6-9 December 2021, Kigali, Rwanda, pp. 1-10. ISBN 978-1-6654-3623-6 (2021) [Refereed Conference Paper]

Copyright Statement

Copyright 2021 IEEE

DOI: doi:10.1109/SPEC52827.2021.9709436


Three-phase induction motors (IMs) are one of the most employed electric machines in industrial and household applications. Condition monitoring of these machines is essential to avoid unplanned maintenance and thereby enhance the availability. Artificial Intelligence (AI) technologies are emerging as an advanced tool for automating condition monitoring process to detect incipient faults at early stages. Machine Learning (ML) algorithms have been identified as a promising approach for condition monitoring of IMs and predicting maintenance to avoid failures. However, selecting the suitable ML algorithm for a given application is challenging because there is no predefined set of application-based algorithms. In addition, raw data processing and feature selection need careful attention to improve the accuracy of the results. This paper reviews supervised ML algorithms that can be used for condition monitoring of IMs and identifies their benefits and drawbacks. It then discusses how the dominant features from raw data can be selected through time domain and frequency domain analysis using the acoustic data collected from a three-phase induction motor. The study investigates classification accuracy of each ML algorithm and a procedure for selecting an algorithm based on the experimental results. Results of this study show that Support Vector Machines (SVM) algorithm outperforms other competing algorithms in condition monitoring of IMs when the dominant frequency components obtained through Fast Fourier Transform (FFT) are used as training data.

Item Details

Item Type:Refereed Conference Paper
Keywords:acoustic signal processing, condition monitoring, induction motor, machine learning
Research Division:Engineering
Research Group:Maritime engineering
Research Field:Marine engineering
Objective Division:Transport
Objective Group:Water transport
Objective Field:International sea freight transport (excl. live animals, food products and liquefied gas)
UTAS Author:Rajapaksha, NN (Mr Nipuna Rajapaksha)
UTAS Author:Jayasinghe Arachchillage, SDG (Dr Shantha Jayasinghe Arachchillage)
UTAS Author:Enshaei, H (Dr Hossein Enshaei)
UTAS Author:Sembukutti Vidanelage, BJ (Dr Nirman Sembukutti Vidanelage)
ID Code:148911
Year Published:2021
Deposited By:Seafaring and Maritime Operations
Deposited On:2022-02-18
Last Modified:2022-07-12

Repository Staff Only: item control page